Planned intervention: On Wednesday June 26th 05:30 UTC Zenodo will be unavailable for 10-20 minutes to perform a storage cluster upgrade.
Published June 25, 2021 | Version v1
Journal article Open

Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning

  • 1. IAS, TU Darmstadt
  • 2. University of Washington

Description

Reactive motion generation problems are usually solved by computing actions as a sum of policies. However, these policies are independent of each other and thus, they can have conflicting behaviors when summing their contributions together. We introduce Composable Energy Policies (CEP), a novel framework for modular reactive motion generation. CEP computes the control action by optimization over the product of a set of stochastic policies. This product of policies will provide a high probability to those actions that satisfy all the components and low probability to the others. Optimizing over the product of the policies avoids the detrimental effect of conflicting behaviors between policies choosing an action that satisfies all the objectives. Besides, we show that CEP naturally adapts to the Reinforcement Learning problem allowing us to integrate, in a hierarchical fashion, any distribution as prior, from multimodal distributions to non-smooth distributions and learn a new policy given them.

Files

CR_2021_COMPOSABLE_URAIN (1).pdf

Files (2.7 MB)

Name Size Download all
md5:a87da13a45cbc4aa28ca2ae16ac376ec
2.7 MB Preview Download

Additional details

Funding

SHAREWORK – Safe and effective HumAn-Robot coopEration toWards a better cOmpetiveness on cuRrent automation lacK manufacturing processes. 820807
European Commission